Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4350 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.3812. Min Act: -0.0000

Data Index: 1568171 (The Pile)

Max Activating Token Index: 594

Text #1

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.4065. Min Act: -0.0000

Data Index: 248055 (The Pile)

Max Activating Token Index: 459

Text #2

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.3977. Min Act: -0.0000

Data Index: 1044188 (The Pile)

Max Activating Token Index: 769

Text #3

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.3887. Min Act: -0.0000

Data Index: 1112295 (The Pile)

Max Activating Token Index: 951

Text #4

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.2394. Min Act: -0.0000

Data Index: 1788778 (The Pile)

Max Activating Token Index: 585

Text #5

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.2966. Min Act: -0.0000

Data Index: 1643434 (The Pile)

Max Activating Token Index: 887

Text #6

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.3559. Min Act: -0.0000

Data Index: 616668 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.1915. Min Act: 0.0000

Data Index: 896621 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.3293. Min Act: -0.0000

Data Index: 859818 (The Pile)

Max Activating Token Index: 768

Text #9

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.2559. Min Act: -0.0000

Data Index: 539386 (The Pile)

Max Activating Token Index: 596

Text #10

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.1780. Min Act: -0.0000

Data Index: 725725 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.3436. Min Act: -0.0000

Data Index: 1195219 (The Pile)

Max Activating Token Index: 922

Text #12

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.1790. Min Act: -0.0000

Data Index: 600585 (The Pile)

Max Activating Token Index: 786

Text #13

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.2352. Min Act: -0.0000

Data Index: 128685 (The Pile)

Max Activating Token Index: 381

Text #14

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.1604. Min Act: -0.0000

Data Index: 824606 (The Pile)

Max Activating Token Index: 400

Text #15

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.2279. Min Act: -0.0000

Data Index: 1632871 (The Pile)

Max Activating Token Index: 951

Text #16

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.3035. Min Act: -0.0000

Data Index: 808992 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.2339. Min Act: -0.0000

Data Index: 1735296 (The Pile)

Max Activating Token Index: 872

Text #18

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.1430. Min Act: -0.0000

Data Index: 1079299 (The Pile)

Max Activating Token Index: 844

Text #19

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.2213. Min Act: -0.0000

Data Index: 648998 (The Pile)

Max Activating Token Index: 295